Skip to Main content Skip to Navigation
Conference papers

Revisiting Monte-Carlo Tree Search on a Normal Form Game: NoGo

C.-W. Chou 1 Olivier Teytaud 2, 3 Shi-Jim Yen 1
3 TAO - Machine Learning and Optimisation
CNRS - Centre National de la Recherche Scientifique : UMR8623, Inria Saclay - Ile de France, UP11 - Université Paris-Sud - Paris 11, LRI - Laboratoire de Recherche en Informatique
Abstract : We revisit Monte-Carlo Tree Search on a recent game, termed NoGo. Our goal is to check if known results in Computer-Go and various other games are general enough for being applied directly on a new game. We also test if the known limitations of Monte-Carlo Tree Search also hold in this case and which improvements of Monte-Carlo Tree Search are necessary for good performance and which have a minor effect. We also tested a generic Monte-Carlo simulator, designed for "no more moves" games.
Document type :
Conference papers
Complete list of metadatas

Cited literature [20 references]  Display  Hide  Download

https://hal.inria.fr/inria-00593154
Contributor : Olivier Teytaud <>
Submitted on : Friday, May 13, 2011 - 2:38:11 PM
Last modification on : Friday, May 1, 2020 - 1:44:04 AM
Document(s) archivé(s) le : Sunday, August 14, 2011 - 2:34:47 AM

File

mogonogo.pdf
Files produced by the author(s)

Identifiers

Collections

Citation

C.-W. Chou, Olivier Teytaud, Shi-Jim Yen. Revisiting Monte-Carlo Tree Search on a Normal Form Game: NoGo. EvoGames 2011, Apr 2011, Turino, Italy. pp.73-82, ⟨10.1007/978-3-642-20525-5⟩. ⟨inria-00593154⟩

Share

Metrics

Record views

626

Files downloads

561